A process and technology advisory firm.

Forecasts that keep their reasoning.

Reckoning Machines builds production systems for investment firms, with AI models inside the research process, and Monte Carlo decision models for corporate finance teams.

Get in touch

Advisory

The work starts inside the client's own forecast.

We build the system and run it alongside the team until it is handed over.

Investment firms

We have twice built a systematic equity platform and taken it through to live trading. The most recent one carries portfolio construction, optimization, order management and execution, with an LLM runner making about 11,000 calls per cycle inside the data pipeline. For a fundamental research team the same engineering puts AI models inside the research process with IRIS.

Corporate finance and FP&A

For a global payments company we built the profitability and unit-economics model for a new product and paired it with Monte Carlo scenario analysis. A large pharmaceutical company needed a way to decide which AI-enabled commercial investments to fund and which to test first. We built that decision framework on Monte Carlo and value-of-information analysis.

Point of view

Cheap models move the value to the process around them.

A frontier model can read a 10-K and draft a forecast assumption at almost no cost, so the cost of building a forecast model has collapsed. Analysis that used to be an edge is becoming a commodity, and the advantage moves to the process around the forecast. Teams that keep their forecasts in one place, with assumptions written down and testable, get more from the same AI models than teams that paste answers into a spreadsheet.

AI that proposes, a record of what it proposed, and a person who decides.

Built by Reckoning Machines

Two systems built on the same rule.

A quarterly operating model open in Excel with Claude alongside, proposing a change to one forecast driver and returning an approval link, nothing run yet — ExcelClaude alongside

IRIS

An IRIS model is a company forecast in Excel that keeps the reasoning behind each key driver, written down as a Method the analyst reviews and approves. IRIS is the catalog of those models, searchable across a portfolio, so a PM can put one question to the whole book and have it answered company by company. The analyst works in Excel with Claude alongside.

Supervised pilot with two investment firms. Access is arranged with us.

irisos.dev

The Dialog workspace on a synthetic desk, showing paper NAV and cash, two competing research questions per cycle with their evidence links, the path from research result through independent check and evidence gate to the paper book, and the research units committed — DialogPaper book

Adaptive Research Harness | DIALOG

Research agents now produce more results than a team can check. The Adaptive Research Harness records every attempt with its cost and checks a result before it enters the accepted record. When a strategy is challenged, the history shows how it was selected. Dialog is the test implementation of ARH.

Open prototypes on GitHub. Synthetic data and paper execution.

View ARH on GitHub View DIALOG on GitHub

About

Run by an investor who builds the systems.

Jed Gore, CFA, started as a software engineer on prime brokerage systems. He then spent nineteen years investing in financial-services stocks, five of them as portfolio manager of a $250 million portfolio at Diamondback Capital. Since 2017 he has built research and analytics platforms for investors. He has been the sole engineer on two systematic equity platforms taken to live trading, and ran the portfolio on one of them. He is a named inventor on a U.S. patent for extracting tables from financial filings.

Writing

The ideas are argued in public before they ship.

Our Substack is where we work out the thinking behind our advisory practice and both systems.

Read on Substack

Contact

One email starts it.

Write to us about a forecast you run or a system you want built.

Email Reckoning Machines